{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:5W4YMWSYI32O2RVAA5CQ5WE2I7","short_pith_number":"pith:5W4YMWSY","schema_version":"1.0","canonical_sha256":"edb9865a5846f4ed46a007450ed89a47e44ff64bc6a5769575fda2f5788bf0ff","source":{"kind":"arxiv","id":"1412.6296","version":2},"attestation_state":"computed","paper":{"title":"Generative Modeling of Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CV","authors_text":"Jifeng Dai, Yang Lu, Ying-Nian Wu","submitted_at":"2014-12-19T11:34:37Z","abstract_excerpt":"The convolutional neural networks (CNNs) have proven to be a powerful tool for discriminative learning. Recently researchers have also started to show interest in the generative aspects of CNNs in order to gain a deeper understanding of what they have learned and how to further improve them. This paper investigates generative modeling of CNNs. The main contributions include: (1) We construct a generative model for the CNN in the form of exponential tilting of a reference distribution. (2) We propose a generative gradient for pre-training CNNs by a non-parametric importance sampling scheme, whi"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1412.6296","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-12-19T11:34:37Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"a6cffa08354ff967c0db41e31e69273dae45219ca36baded2ce181ff59b5be8a","abstract_canon_sha256":"5576cea52457e5fac7c6dc45f8388a39e7641f7308586b4b6e52af723f7d27db"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:19:16.359914Z","signature_b64":"vaAbJucbCgISTBvx7OPkdp7HUlEcBOzJJi/Yg7gzSmxu4zHdo58iZZzg0vRAcstg8fQGTISEeHRFgibM0pNbCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"edb9865a5846f4ed46a007450ed89a47e44ff64bc6a5769575fda2f5788bf0ff","last_reissued_at":"2026-05-18T02:19:16.359226Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:19:16.359226Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generative Modeling of Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CV","authors_text":"Jifeng Dai, Yang Lu, Ying-Nian Wu","submitted_at":"2014-12-19T11:34:37Z","abstract_excerpt":"The convolutional neural networks (CNNs) have proven to be a powerful tool for discriminative learning. Recently researchers have also started to show interest in the generative aspects of CNNs in order to gain a deeper understanding of what they have learned and how to further improve them. This paper investigates generative modeling of CNNs. The main contributions include: (1) We construct a generative model for the CNN in the form of exponential tilting of a reference distribution. (2) We propose a generative gradient for pre-training CNNs by a non-parametric importance sampling scheme, whi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1412.6296","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1412.6296","created_at":"2026-05-18T02:19:16.359335+00:00"},{"alias_kind":"arxiv_version","alias_value":"1412.6296v2","created_at":"2026-05-18T02:19:16.359335+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1412.6296","created_at":"2026-05-18T02:19:16.359335+00:00"},{"alias_kind":"pith_short_12","alias_value":"5W4YMWSYI32O","created_at":"2026-05-18T12:28:16.859392+00:00"},{"alias_kind":"pith_short_16","alias_value":"5W4YMWSYI32O2RVA","created_at":"2026-05-18T12:28:16.859392+00:00"},{"alias_kind":"pith_short_8","alias_value":"5W4YMWSY","created_at":"2026-05-18T12:28:16.859392+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5W4YMWSYI32O2RVAA5CQ5WE2I7","json":"https://pith.science/pith/5W4YMWSYI32O2RVAA5CQ5WE2I7.json","graph_json":"https://pith.science/api/pith-number/5W4YMWSYI32O2RVAA5CQ5WE2I7/graph.json","events_json":"https://pith.science/api/pith-number/5W4YMWSYI32O2RVAA5CQ5WE2I7/events.json","paper":"https://pith.science/paper/5W4YMWSY"},"agent_actions":{"view_html":"https://pith.science/pith/5W4YMWSYI32O2RVAA5CQ5WE2I7","download_json":"https://pith.science/pith/5W4YMWSYI32O2RVAA5CQ5WE2I7.json","view_paper":"https://pith.science/paper/5W4YMWSY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1412.6296&json=true","fetch_graph":"https://pith.science/api/pith-number/5W4YMWSYI32O2RVAA5CQ5WE2I7/graph.json","fetch_events":"https://pith.science/api/pith-number/5W4YMWSYI32O2RVAA5CQ5WE2I7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5W4YMWSYI32O2RVAA5CQ5WE2I7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5W4YMWSYI32O2RVAA5CQ5WE2I7/action/storage_attestation","attest_author":"https://pith.science/pith/5W4YMWSYI32O2RVAA5CQ5WE2I7/action/author_attestation","sign_citation":"https://pith.science/pith/5W4YMWSYI32O2RVAA5CQ5WE2I7/action/citation_signature","submit_replication":"https://pith.science/pith/5W4YMWSYI32O2RVAA5CQ5WE2I7/action/replication_record"}},"created_at":"2026-05-18T02:19:16.359335+00:00","updated_at":"2026-05-18T02:19:16.359335+00:00"}